# Research Papers — 2026-05 · bundle page 201 of 326 > Full-text markdown of papers #10001–10050 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-05/page/201 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/200.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/202.md) ### STARS: Spike Tail-Aware Relational Synthesis for ANN-to-SNN Data-Free Knowledge Distillation Authors: Shuhan Ye, Yi Yu, Qixin Zhang, Hui Lu, Jiaming He, Qinggang Zhang, Li Shen, Xudong Jiang Published: 2026-05-12 Categories: cs.NE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.27409v1 SNNs promise energy-efficient and low-latency inference, but their performance still trails that of ANNs. ANN-to-SNN knowledge distillation helps narrow this gap, yet the original training data are often unavailable in practical deployment settings. Existing data-free knowledge distillation (DFKD) methods synthesize surrogate data by matching teacher-side priors, especially BN statistics, but these ANN-oriented constraints mainly regularize mean and variance and therefore remain under-constrained for SNN students whose responses depend on threshold-crossing dynamics. In this paper, we propose Spike Tail-Aware Relational Synthesis (STARS), a plug-and-play method for ANN-to-SNN DFKD that augments standard BN-guided synthesis with two complementary objectives: Relational Consistency Alignment, which preserves cross-sample relational consistency between teacher and student, and Tail-Aware Regularization, which regularizes threshold-relevant tail probabilities through soft exceedance over teacher-derived thresholds. Together, these objectives generate synthetic batches that remain teacher-valid while becoming more informative for SNN students. Experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet across multiple ANN-SNN pairs show that our method consistently improves conventional DFKD baselines and even surpasses several KD methods, with gains of up to 4.6\% on CIFAR-10 and 6.7\% on CIFAR-100, highlighting the importance of complementing BN matching with relational and tail-aware constraints in SNN-oriented DFKD. --- ### Neural Quantum Spectral Operator Learning for Solving Partial Differential Equations Authors: Chanyoung Kim, Myeonghwan Seong, Yujin Kim, Daniel K. Park, Youngjoon Hong Published: 2026-05-12 Categories: quant-ph, cs.LG, math.NA arXiv: https://arxiv.org/abs/2605.27408v1 Partial differential equations (PDEs) are central to modeling physical and engineering systems, but repeatedly solving parametric PDEs remains computationally expensive. Operator learning enables fast surrogate inference, yet typically requires large input-output paired datasets generated by costly high-fidelity PDE solvers. Unsupervised operator learning frameworks alleviate data dependency but remain hindered by computational bottlenecks. To address this, we propose Neural Variational Quantum Linear Solver (NVQLS), the first hybrid quantum-classical operator learning framework leveraging the Legendre--Galerkin weak formulation. We critically resolve the sign ambiguity in VQLS energy minimization, preventing erroneous solution representations. Additionally, we introduce a neural embedding, a novel encoding scheme to map varying forcings and PDE coefficients into parameterized quantum circuit representations. These structural innovations provide theoretical computational complexity advantages under efficient state preparation schemes, while achieving superior accuracy compared to a representative classical baseline. Validations on 1D and 2D parametric PDEs under diverse boundary conditions demonstrate NVQLS's capability to simultaneously process varying inputs, offering a scalable unsupervised approach to quantum-enhanced operator learning. --- ### TriVAL: A Tri-Validation Framework for Faithful Automatic Optimization Modeling Authors: Ziyang Fang, JinXi Wang, Jinghui Zhong, Yew-Soon Ong Published: 2026-05-12 Categories: cs.CL, cs.AI, eess.SY, math.CO arXiv: https://arxiv.org/abs/2605.23966v1 Optimization modeling serves as the pivotal bridge between natural-language problem descriptions and optimization solvers, and remains a cornerstone for bringing operations research (OR) into real-world decision making. Recent advances in large language models (LLMs) have driven significant progress in automatic optimization modeling. However, existing methods still lack explicit validation during the modeling process, allowing errors introduced in earlier stages to carry through the pipeline and ultimately reduce final modeling accuracy. To address this challenge, we introduce TriVAL, a tri-validation framework that performs explicit validation at three stages of automatic optimization modeling: semantic specification, mathematical formulation, and code generation. At each stage, TriVAL follows a construct-validate-revise loop that assesses the current result against stage-specific criteria and revises it when needed. This design helps identify and correct errors before they accumulate across stages, helping preserve faithfulness throughout the modeling process. To evaluate automatic optimization modeling on more challenging combinatorial problems, we further introduce NL4COP, a benchmark of 150 instances across 50 diverse problem types with more complex decision logic, more tightly coupled constraints, and more demanding modeling requirements than existing benchmarks. Experiments on NL4COP and established benchmarks show that TriVAL consistently outperforms state-ofthe-art methods, with the largest gains on the most challenging problems. --- ### LGMT: Logic-Grounded Metamorphic Testing for Evaluating the Reasoning Reliability of LLMs Authors: Zenghui Zhou, Man Li, Xiaoke Fang, Xinyi Zhou, Weibin Lin, Zheng Zheng Published: 2026-05-12 Categories: cs.AI, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2605.23965v3 Large Language Models (LLMs) achieve strong performance on logical reasoning benchmarks, yet their reliability remains uncertain. Existing evaluations rely on static benchmarks, which fail to assess robustness under logically equivalent transformations and often overestimate reasoning capability. We propose LGMT (Logic-Grounded Metamorphic Testing), an oracle-free framework that leverages first-order logic (FOL) to evaluate LLM reasoning. By deriving metamorphic relations from formal logical equivalences, LGMT constructs semantically invariant test cases and detects reasoning defects through cross-case consistency checking. Experiments on six state-of-the-art LLMs show that LGMT exposes substantial hidden defects missed by traditional reference-based evaluations. We further find that models are particularly sensitive to symbol-level and conclusion-level variations, and that advanced prompting such as Few-shot CoT only partially mitigates these issues. These results suggest that LLM evaluation should move beyond isolated correctness toward robustness under logical invariance. LGMT provides a principled and scalable approach for diagnosing reasoning failures. --- ### Multi-market value-stacking: Battery control for combined imbalance participation and non-uniform FCR bidding Authors: Celle Hendrickx, Fabio Pavirani, Chris Develder Published: 2026-05-12 Categories: eess.SY, cs.AI arXiv: https://arxiv.org/abs/2605.23964v1 The growing share of Renewable Energy Sources (RES) in modern power systems increases both grid imbalances and frequency deviations, reinforcing the need for ancillary services such as Frequency Containment Reserve (FCR) and passive balancing. Battery Energy Storage Systems (BESS) are well-suited for these services, but prior research typically relies on uniform FCR bids that remain constant throughout the control period. Such static bids fail to fully exploit BESS flexibility, as they do not balance the trade-off between reserving energy for FCR delivery and using it for imbalance arbitrage, limiting the achievable value in value-stacking settings. To address this limitation, we propose a two-stage control framework for the European context that introduces non-uniform FCR bids. In the first stage, we derive a time-varying bid sequence using data-driven Monte Carlo (MC) optimization. In the second stage, a Deep Reinforcement Learning (DRL) agent leverages the residual flexibility for real-time imbalance trading while proactively managing the State of Energy (SoE) to ensure compliance with FCR requirements. The framework is presented as a proof of concept, highlighting the potential benefits of time-varying bidding strategies. By incorporating daily cycle budgets and time-varying reserve commitments, our approach achieves a 7.56% profit increase compared to uniform baselines. These results show that non-uniform bidding can unlock additional value by more effectively aligning reserve obligations with rapidly changing imbalance opportunities. --- ### From Index to Equity: Pre-Training Transformers for Stock Return Prediction Authors: Marie Soehl Coolsaet, Roberto Gallardo, Zhen Gao Published: 2026-05-12 Categories: q-fin.ST, cs.LG arXiv: https://arxiv.org/abs/2605.23962v1 This research aims to leverage machine learning to improve stock price prediction and support informed investment decisions related to buying, selling, and holding assets. Specifically, this work investigates transformer-based models for stock prediction and examines the impact of pre-training strategies on forecasting performance. A transformer model was first pre-trained on the Toronto Stock Exchange Index (TSX) to predict intra-day return direction and subsequently fine-tuned on individual TSX stocks. The model was further adapted for return-value regression tasks. Performance was benchmarked against Long Short-Term Memory (LSTM) and XGBoost models. Pre-training on the market index improved the binary cross-entropy loss for individual stock prediction from 0.69 to 0.64. The fine-tuned transformer regression model achieved lower mean squared error than the benchmark models, although the ensemble and XGBoost models achieved higher average daily returns. In addition, a practical application was developed to deliver real-time stock predictions for trading support. Future work will focus on increasing transformer model capacity, incorporating broader global technical indicators, and filtering out stocks with low predictability. --- ### Multimodal Alignment and Preference Optimization for Zero-Shot Conditional RNA Generation Authors: Roman Klypa, Alberto Bietti, Sergei Grudinin Published: 2026-05-12 Categories: q-bio.BM, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.23961v1 The design of RNA molecules that interact with specific proteins is a critical challenge in experimental and computational biology. Despite recent progress in natural language modeling and deep learning-based protein design, there remains significant room to improve the frequency of successful interactions and the authenticity of generated sequences for functional applications. In this work, we frame conditional RNA sequence generation as a multi-stage alignment problem, introducing Moirain: a suite of models optimized via multimodal supervised fine-tuning (SFT) and Direct Preference Optimization (DPO). Our approach begins with large-scale pretraining on diverse RNA corpora to capture the fundamental grammars of sequence plausibility. To achieve target-specific generation, we employ a multimodal SFT architecture that conditions RNA synthesis on protein structural and sequential features. Finally, we leverage DPO to refine the model using synthetic interaction data: taking advantage of DPO's unique ability to navigate non-aligned preference spaces, we improve functional fitness without collapsing the learned natural distribution. Extensive evaluation of the Moirain series (Moirain-Base, -Multi, and -DPO) demonstrates that our framework consistently produces novel, diverse, and biologically plausible RNA sequences with superior binding affinities compared to existing baselines. --- ### Learning Protein Structure-Function Relationships through Knowledge-guided Representation Decomposition Authors: Mingqing Wang, Zhiwei Nie, Athanasios V. Vasilakos, Yonghong He, Zhixiang Ren Published: 2026-05-12 Categories: q-bio.BM, cs.LG arXiv: https://arxiv.org/abs/2605.23960v1 Proteins encode diverse functions within complex three-dimensional structures, yet most deep learning representations remain highly entangled, obscuring the biophysical signals that underlie function. Here we introduce ProtDiS, a knowledge-guided framework that decomposes pretrained protein micro-environment embeddings into biologically grounded and task-relevant dimensions. Inspired by the information bottleneck principle, ProtDiS learns representations that balance informativeness and compression, yielding structural features that are more specific, independent, and information-efficient, and achieving consistent improvements across twelve downstream tasks, with the largest gains under structure-based splits. Protein- and residue-level analyses further show that ProtDiS differentiates proteins with similar folds but divergent functions and captures fine-grained biophysical signals critical. These findings suggest that knowledge-guided decomposition provides a general and interpretable approach for structuring latent spaces in protein structural modeling. The source code and implementation details are publicly available at https://github.com/AI-HPC-Research-Team/ProtDiS. --- ### The Misattribution Gap: When Memory Poisoning Looks Like Model Failure in Agentic AI Systems Authors: Tanzim Ahad, Ismail Hossain, Md Jahangir Alam, Sai Puppala, Syed Bahauddin Alam, Sajedul Talukder Published: 2026-05-12 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.22842v1 Multi-agent AI pipelines typically assume that agent misconduct originates from model misalignment. We identify a structural failure in this assumption, the \emph{Misattribution Gap}, where memory-layer attacks produce behaviors indistinguishable from model failure, causing defenders to apply the wrong remediation. We formalize \emph{Semantic Norm Drift} (SND) as a third path to agent misconduct, distinct from emergent misalignment and collusion. In SND, a policy-formatted document enters a shared vector store through normal uploads and later reappears as trusted system context after provenance is lost through a Trust Laundering Chain. Across 64 documented failures, attribution systems consistently blamed the model. Four safety classifiers, including one trained on memory poisoning, produced zero detections across 510 checkpoints. In 59 of 65 valid cases, agents explicitly cited the injected document as normative authority before complying. The attack requires no trigger, model access, or repeated interaction, achieves full effect within five sessions, and persists indefinitely. We introduce Counterfactual Composition Testing, which identifies the causal entry with 87.5% accuracy and zero false positives, while a forensics baseline fails across all 25 scenarios. We further prove the Retrieval-Coverage Dilemma, showing that stronger evasion inherently weakens the attack, limiting adaptive bypass strategies. Finally, we propose Memory-Persistent Information-Flow Control, which blocks 97% of attacks at the cross-session boundary where prior defenses fail. We release the SND Corpus, the first adversarial memory benchmark with temporal persistence and multi-agent composition across financial and Health Care domains. --- ### Advanced Scientific Methodology Plays Rossini Authors: Silvia Licciardi, Daniela Macchione, Emmanuel Caronna, Elisa Francomano Published: 2026-05-12 Categories: cs.SD, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2605.20220v1 A musical score provides the essential instructions for its performance while containing indications - at times implicit - regarding the composer's intentions. The presence of authorial variants, and even more so complex series of revisions associated with a single text, presents a challenging path for analytical study. This research, situated within the application of Scientific Methodologies to Music Philology, proposes a methodological approach oriented toward the structural analysis of one of the many settings composed by Gioachino Rossini on the same Metastasio arietta ``Mi lagnerò tacendo''. Through Computational Analysis - incorporating parsing, data mining, and graph theory - the melodic, harmonic, and textual compositional choices have been rigorously explored. The results constitute a significant unicum in the field, laying the foundation for a systematic study that supports philological research and paves the way for the use of generative models to investigate the creative process. --- ### Sparse Mixture-of-Experts Routing in Visual Diffusion Transformers:Diagnosis, Boundary Calibration and Evolutionary Roadmap from Routing Collapse to Selective Deadlock Authors: Haiying Sha Published: 2026-05-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.19378v1 This paper systematically diagnoses the training failure modes of Token-Choice sparse Mixture-of-Experts (MoE) on video Diffusion Transformers. Starting from a pretrained dense model of about 5 billion parameters, we convert it into an MoE architecture following three laws: routed experts exactly clone the original FFN weights, shared experts are initialized to zero for verification and then to extremely small non-zero noise for actual training, while only the gating networks start from random initialization. Experiments reveal a hierarchy of five failure modes: (1) linear routers suffer global soft saturation with complete expert homogenization; (2) MLP routers introduce selective deadlock, where roughly one-third of layers degenerate into a single-expert mode that cannot be prevented by increasing the auxiliary loss; (3) cross-attention routers exhibit preliminary self-recovery, yet about nine layers remain stubbornly deadlocked; (4) deadlocked layers display a U-shaped distribution, concentrated in shallow visual processing layers and deep semantic integration layers; (5) bfloat16 mixed precision causes tiny weight updates to be truncated to zero by hardware. Based on routing decision time series over 65 million tokens across 5,000 training steps, we propose the Functional Redundancy Hypothesis: deadlock is a rational waiting strategy before the shared expert matures within the gate-shared expert-routed expert triadic system. This hypothesis is supported by the theory of functional redundancy in systems biology. On the engineering side, we summarize the Three Laws of dense-to-MoE conversion and provide a complete solution for the bfloat16 precision trap. We calibrate the current capability boundary of the Token-Choice paradigm and outline a three-step evolutionary roadmap from visual unification to a world model. --- ### Automated Big Data Quality Assessment using Knowledge Graph Embeddings Authors: Hadi Fadlallah, Rima Kilany, Mitri Haber, Ali Jaber Published: 2026-05-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.18833v1 Automated data quality assessment is crucial for managing big data, but existing solutions face challenges in achieving accurate context-aware assessment. This paper presents a novel knowledge-based approach to enhance automated data quality assessment. Our approach utilizes knowledge graph embeddings to predict missing edges between the input dataset's context representation and the relevant quality rules and dimensions within a knowledge graph representing contextual data characteristics and the required quality assessment operations. We surpass conventional practices by integrating diverse representations within the knowledge graph, drawing insights from contextual information from a thorough literature investigation. This integration allows us to develop a comprehensive and context-specific data quality assessment plan tailored to each context. Leveraging the knowledge graph improves our understanding of the input dataset's context, overcoming the limitations of traditional methods that rely solely on strict matching and overlook contextual characteristics. By injecting numerical edge attributes, we assign corresponding weights to each predicted quality measurement, providing a comprehensive data quality assessment plan for the input dataset. To evaluate our approach, we leverage AmpliGraph, a framework developed and benchmarked by AccentureLabs. The evaluation involves employing a real-world radiation sensors dataset provided by the Lebanese Atomic Energy Commission (LAEC-CNRS). The results obtained from this evaluation demonstrate the capability of our solution to generate a comprehensive data quality assessment plan for the given input dataset. --- ### Precision Tracked Transformer via Kalman Filtering, Kriging and Process Noise Authors: Bo Long, Deepak Agarwal, Jelena Markovic-Voronov, Yi Wang, Liuqing Li Published: 2026-05-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.18832v1 The Transformer is the foundational building block of modern AI, yet offers no principled handling of \emph{uncertainty}, which is prevalent in real applications: cold-start tokens with sparse histories in sequential recommendation, heterogeneous signal quality in language models, and attention sinks induced by unconstrained softmax. Every token is treated with uniform confidence. We show this uniformity is a degenerate case of our \emph{Bayesian Filtering Transformer} (BFT): attention becomes precision-weighted kriging, the residual connection becomes a Kalman update with adaptive gain, and the FFN becomes a dynamics model propagating precision via a Jacobian--plus--process-noise rule. Observation precision comes from a parameter-free Restricted Maximum Likelihood (REML) estimator with a conjugate Bayesian prior. BFT replaces any Transformer layer with negligible overhead. On sequential recommendation, BFT applied to three major architectures yields significant gains on six benchmarks, with the largest improvements on cold-start users and rare items where uncertainty is highest. On supervised fine-tuning of large language models with noisy data, BFT improves robustness in two regimes: noisy supervision (token-label corruption in question answering) and noisy context (retrieval-augmented QA with real RAG distractors). A single principled modification -- restoring precision -- unlocks substantial headroom across both classical sequence-modeling and modern LLM regimes. --- ### Towards Discovery of Polymers for Insulin Delivery via Physics-Grounded Agentic Workflows Authors: Martins Otun Published: 2026-05-12 Categories: q-bio.QM, cs.LG arXiv: https://arxiv.org/abs/2605.18831v1 Cold-chain storage limits access to insulin for hundreds of millions of people; a thermally protective patch polymer could help, but the design space is too large for exhaustive experiment. Starting from that problem, we narrow to an agentic workflow: a large language model (LLM) calls physics-based tools through the Model Context Protocol (MCP), searching the discrete PSMILES space under a budget of OpenMM Packmol-matrix evaluations. The LLM acts as an implicit acquisition function conditioned on a persistent "discovery world": hypotheses, literature claims, and simulation outcomes updated each iteration. Under matched oracle budgets, the best autonomous campaign reaches an insulin-polymer interaction energy of -2263 kJ/mol, outperforming reinforcement-learning baselines by 68% and Bayesian optimization by 19%. Three independent campaigns converge on one structural motif (dense hydrogen-bond donors and acceptors per repeat unit) while physics checks reject infeasible packings and name-structure mismatches before they steer the next step. The science stage is CPU-bound and runs on commodity hardware. More broadly, the same architecture and workflow designed here applies to other protein-stabilization tasks whenever a tractable screening oracle is available. --- ### In-Context Learning Operates as Concept Subspace Learning Authors: Wei Tang, Xinyan Jiang, Fakhri Karray, Lijie Hu Published: 2026-05-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.18830v1 Regression and Bayesian accounts of in-context learning (ICL) explain how demonstrations can induce predictors, while mechanistic analyses often identify compact activation directions that steer prompted behavior. However, it remains unclear whether structured demonstrations induce low-dimensional concept inference. We study this question through a concept-subspace view of ICL, in which tasks vary only along intrinsic concept coordinates, although inputs are observed in a high-dimensional ambient space. For ridge and least-squares ICL proxies, prediction decomposes exactly into concept-coordinate regression and off-subspace leakage. Under block-diagonal or near-block-diagonal covariance assumptions, the leading estimation and nuisance-sensitivity terms scale with the dimension of the concept subspace, while residual effects are controlled by cross-subspace coupling. This separation gives a mechanistic prediction: recoverable task information should concentrate in a low-dimensional, task-aligned activation subspace. On CounterFact-derived multi-relation prompts with Llama-3-8B, a 68--73-dimensional subspace of the 4096-dimensional residual stream restores 78.8% of the clean--corrupted accuracy gap, whereas patching the complementary subspace restores 0%. Concept swaps redirect predictions toward injected relations, while random and cross-task matched-rank controls are largely ineffective. Additional experiments on Qwen2.5-7B and a controlled cross-lingual rule task show the same qualitative pattern. These results support concept subspaces as compact, task-aligned mediators of recoverable ICL behavior in structured task families, without implying full-circuit recovery. --- ### Lossless Anti-Distillation Sampling Authors: Zibo Diao, Jingchu Gai, Xinyue Ai, Zhang Zhang, Zhenyu He, Di He Published: 2026-05-12 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2605.18829v2 Frontier commercial generative models face a growing threat from distillation, whereby a distiller harvests generated responses and trains a competing model at drastically lower cost. Existing defenses either modify the generation to degrade distillation performance, sacrificing response quality, or rely on behavioral detection mechanisms that can be readily bypassed through multi-account querying. In this work, we propose Lossless Anti-Distillation Sampling (LADS), which leaves the generation itself unchanged while substantially reducing the effectiveness of distillation. Concretely, LADS controls the latent randomness underlying inference through a coupling mechanism that preserves within-account generation independence while inducing cross-account dependence. By construction, each benign user, who typically holds only a single account, receives the same experience under LADS as they would without any defense, thereby enjoying a lossless experience. However, for a multi-account task-specific distiller, semantically similar queries submitted across different accounts are assigned coupled randomness, inducing dependence in the harvested data and thereby degrading the generalization performance of the distilled model. Using uniform convergence theory, we show that LADS provably degrades the distiller's generalization gap relative to standard i.i.d. sampling. Experiments on image generation, mathematical reasoning, and code generation confirm that LADS substantially degrades the performance of distilled students while preserving exact statistical fidelity for individual users. --- ### Lossless Anti-Distillation Sampling Authors: Zibo Diao, Jingchu Gai, Xinyue Ai, Zhang Zhang, Zhenyu He, Di He Published: 2026-05-12 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2605.18829v1 Frontier commercial generative models face a growing threat from distillation, whereby a distiller harvests generated responses and trains a competing model of its own at drastically lower cost. Existing defenses either rely on modifying the models outputs, thereby sacrificing response quality for benign users, or on behavioral detection methods, which can be readily circumvented by distributing queries across multiple accounts. In this work, we propose Lossless Anti-Distillation Sampling (LADS), a novel sampling scheme specifically designed to counter multi-account distillation while maintaining a lossless experience for benign users. Concretely, LADS derives the randomness underlying each generation from a private seed determined by the semantic content of the query and the number of times the user has queried the model. By construction, every benign user receives a response independently sampled from the original model at each visit, and thus experiences no distortion. In contrast, for a distiller, different accounts share latent randomness whenever their queries fall in the same semantic bucket. As a result, the harvested data becomes correlated, potentially reducing sample diversity and degrading generalization. Using uniform convergence theory, we show that LADS provably degrades the convergence rate of the distillers generalization gap relative to standard i.i.d. sampling in both unconditional and conditional generation settings. Experiments on image generation, mathematical reasoning, and code generation confirm that LADS substantially degrades the performance of distilled students while preserving exact statistical fidelity for individual users. --- ### Code-Guided Reasoning for Small Language Models: Evaluating Executable MCQA Scaffolds Authors: Prateek Biswas, Dhaval Patel, Vedant Khandelwal, Shuxin Lin, Amit Sheth Published: 2026-05-12 Categories: cs.IR, cs.LG, cs.PL arXiv: https://arxiv.org/abs/2605.18827v1 Multiple-choice QA benchmarks usually evaluate small language models (SLMs) as direct answerers, but deployed language-model systems increasingly rely on external scaffolds such as tools, code, and repeated model calls. We introduce Code-Guided Reasoning (CGR), an evaluation protocol and generated-program resource for measuring when executable reasoning scaffolds improve SLM performance on MCQA tasks. CGR standardizes six components: a normalized item interface, a direct solver prompt, a generator prompt, a Python scaffold, solver-call and extraction helpers, and a three-channel result record. On 20,498 retained result rows from a locally prepared MCQA bundle and six metadata-registered solver models, the observed non-zero-baseline partition shows 66.21% macro assisted accuracy versus 38.11% direct accuracy, a +28.10 percentage-point difference with a pair-bootstrap interval of (20.32, 36.43). Under a stricter Ab > 30% direct-signal gate, the macro difference is +14.11 points. These estimates are descriptive. Assisted inference uses a larger solver-call budget, answer extraction is brittle, Time-MQA contains the observed regressions, and some generated programs violate the no-hard-coding instruction. CGR provides the trace package needed to interpret these results, including direct, assisted, and generator-side answers, partition definitions, generated programs, response metadata, and audits. --- ### The Routing and Filtering Structure of Attention Authors: Shafayeth Jamil, Rehan Kapadia Published: 2026-05-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.18826v1 The attention interaction matrix $QK^{\top}$ contains two entangled computations: a skew-symmetric component that redistributes information between positions (routing) and a symmetric component that scales mutual relevance (filtering). We decompose 1776 heads across five pretrained transformers and find routing operating at low rank, well below the routing capacity allocated by the weight kernel. We introduce $S$-$D$ attention as a diagnostic parameterization that disentangles routing from filtering by construction with guaranteed stability ($\mathrm{Re}(λ) \le 0$) and trains stably without layer normalization. When disentangled and unnormalized, routing self-organizes into a spectral cascade, effective rank $2$ at the first layer, expanding with depth across six scales from 7M to 355M parameters. The cascade predicts where attention can be simplified: linearizing the first seven layers of 125M $S$-$D$ attention costs ${<}5\%$ perplexity, whereas standard attention collapses under the same intervention. The linearizable region widens with depth. Replacing the first four layers with ELU+1 linear attention reaches within $1.4\%$ of baseline at full head dimension. Cascade-allocated architectures trade attention parameters for perplexity ($47\%-65\%$ fewer attention parameters at $+3.9\%$ to $+8.4\%$ PPL). The routing-filtering decomposition makes the spectral budget legible; the cascade makes it actionable. --- ### Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches Authors: Shaoke Fang, Ziang Li, Wenfei Wu, Jiatong Ji, Qingsong Liu, Ruizhi Pu Published: 2026-05-12 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2605.18825v1 Prefix caching is a key optimization in Large Language Model (LLM) serving, reusing attention Key-Value (KV) states across requests with shared prompt prefixes to reduce expensive prefill computation. However, its benefit depends critically on the eviction policy as GPU memory is scarce, and existing policies such as LRU largely treat cached blocks uniformly. This view ignores a fundamental property of LLM prompts: not all tokens are equally worth caching. We show that different token types within a prompt, including system prompts, user queries, tool outputs, model responses, and chain-of-thought reasoning, exhibit up to 756x variation in reuse rates, yet no existing eviction policy exploits this signal. In this paper, we present SAECache (Semantic-Adaptive Eviction for prefix caches), a semantic-adaptive prefix cache eviction policy that addresses this gap through three innovations: (1) a multi-queue architecture that routes KV blocks to task-specific queues with tailored priority metrics, capturing both session reuse in multi-turn requests and structural reuse in templated single-turn requests; (2) a semantic-aware token weighting mechanism that learns the reuse value of different token types online through eviction feedback; and (3) a fully adaptive online learning schema for all parameter updates, including log-normal timing parameters, position decay power, queue weights, and meta-parameters, which eliminates manual tuning and enables automatic adaptation to deployment-specific workload characteristics. Through extensive evaluation across heterogeneous workloads, we demonstrate that SAECache achieves 1.4x-2.7x TTFT improvement over production-style baselines, while fixed-parameter alternatives can degrade by up to 2.7x under workload mismatch -- a failure mode our adaptive approach avoids entirely. --- ### Fine-Grained Benchmark Generation for Comprehensive Evaluation of Foundation Models Authors: Mohammed Saidul Islam, Negin Baghbanzadeh, Farnaz Kohankhaki, Afshin Cheraghi, Ali Kore, Shayaan Mehdi, Elham Dolatabadi, Arash Afkanpour Published: 2026-05-12 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.18824v1 Evaluation of foundation models often rely on aggregate scores from benchmarks that lack comprehensive coverage and metadata for a fine-grained evaluation. We introduce a framework for automated benchmark generation. Our framework generates evaluation problems grounded in reference material, such as textbooks, producing benchmarks with broad coverage, rich metadata, and robustness to contamination. The pipeline employs a multi-agent architecture for problem generation and a solution-graph-driven strategy that significantly improves the reliability of ground truth solutions. Using the framework, we generate three benchmarks in Machine Learning, Corporate Finance, and Personal Finance. Expert review finds a significantly lower ground-truth error rate than previous benchmarks such as MMLU and GSM8K. Evaluation of 12 commercial and open-source models shows that our benchmarks achieve near-uniform competency coverage and surface performance differences across models that existing benchmarks fail to capture. We will open-source the framework and our curated benchmarks soon. --- ### Multi-Pedestrian Safety Warning at Urban Intersections Use Case of Digital Twin Authors: Yongjie Fu, Qi Gao, Mahshid Ghasemi Dehkordi, Gil Zussman, Xuan Di Published: 2026-05-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.18823v1 Digital twins (DTs) for urban transportation systems have gained increasing attention; however, their systematic evaluation in safety-critical scenarios remains limited. This paper presents a multi-pedestrian safety warning system at urban intersections enabled by a tightly coupled physical-digital twin framework. Built upon the COSMOS city-scale wireless testbed in New York City, the proposed system integrates camera and ultra-wideband (UWB), edge-cloud computing, predictive trajectory modeling, and MQTT-based communication to deliver real-time safety alerts to vulnerable road users (VRUs). The system is evaluated through both field deployment and virtual reality (VR) experiments. Results demonstrate high warning generation accuracy, localization accuracy, efficient end-to-end latency under different model configurations, and significant reductions in user response time when warnings are issued. The proposed DT framework provides a scalable, modular, and generalizable solution for real-time multi-pedestrian safety enhancement at complex urban intersections. --- ### Hybrid-LoRA: Bridging Full Fine-Tuning and Low-Rank Adaptation for Post-Training Authors: Chengqian Zhang, Wei Zhu, Kyumin Lee Published: 2026-05-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.18822v1 Post-training has become essential for adapting large language models (LLMs) to complex downstream behaviors, including instruction following, preference alignment, and multi-step reasoning. Reinforcement learning with verifiable rewards (RLVR) has recently emerged as a particularly effective post-training paradigm for improving reasoning capabilities, with critic-free algorithms such as GRPO and GSPO enabling scalable optimization. However, RLVR post-training with full fine-tuning (FFT) requires substantial GPU memory and incurs high training costs. Although parameter-efficient fine-tuning (PEFT) methods, such as Low-Rank Adaptation (LoRA), effectively reduce computational costs, they often suffer from a noticeable performance gap compared to full fine-tuning in post-training for complex reasoning tasks. In this paper, we propose Hybrid-LoRA, an efficient hybrid post-training framework that selectively applies full fine-tuning to a small subset of modules less suited to low-rank adaptation, while adapting the remaining components with LoRA. We introduce a novel Hybrid-LoRA Score to rank candidate modules according to their sensitivity to low-rank adaptation under a fixed parameter budget. Experiments show that Hybrid-LoRA closely matches full fine-tuning performance under a 10% full fine-tuning module budget, with the remaining candidate modules adapted by LoRA, consistently outperforming four state-of-the-art PEFT post-training baselines, achieving improvements of up to 5.65% and on average 4.36% over the best baseline. --- ### Quantum Adversarial Machine Learning: From Classical Adaptations to Quantum-Native Methods Authors: Roozbeh Razavi-Far, Mohammad Meymani, Erfan Mahmoudinia, Dorsa Vazirzade, Peyman Paknezhad, Fateme Ghasemi, Saeed Saravani, Somayeh Nikkhoo, Kimia Haghjooei Published: 2026-05-12 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2605.18821v1 Machine learning has revolutionized numerous industrial domains. Despite recent advances, machine learning models remain vulnerable to adversarial threats. Adversarial machine learning is a field that studies these vulnerabilities to build robust machine learning models. Quantum machine learning is an interdisciplinary field that bridges quantum computing and classical machine learning. While quantum machine learning shows potentials to outperform classical machine learning in complex tasks such as regression, classification, and generative modeling, it remains vulnerable to adversarial attacks. Given the recent advancements in quantum computing and machine learning, the quantum adversarial machine learning field has emerged to study the vulnerabilities of quantum machine learning, possible attacks, and novel quantum-enhanced defense strategies. In this survey, we provide a detailed overview on quantum adversarial machine learning and explore the existing attacks and countermeasures. We also review the theoretical underpinnings of this area, emerging trends, and critical challenges. --- ### Emergence of Frontier Superposition: Möbius attractor and Cascade Supervision Authors: Hongyu Gu, Jingwen Fu Published: 2026-05-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.18820v1 Superposition allows Transformers to reason in depth, carrying an entire reasoning frontier in parallel through a bounded-depth forward pass instead of unrolling serial chain-of-thought tokens. While Zhu et al. (2025) hand-crafted an equal-weight breadth-first frontier in a single residual stream for graph reachability, it remained open whether gradient descent could ever find this target amidst permutation-symmetric saddles. We close this gap on Reachability-by-Superposition over Erdős-Rényi graphs by isolating architectural and supervisional contributions. Architecturally, we identify a Möbius attractor: under $S_n$-symmetry in the tree regime, layerwise dynamics reduce to a 1D Möbius map whose zero set is a codimension-one manifold of global optima containing the equal-weight superposition state. On the supervision side, we identify Cascade Supervision: a loss class whose backward pass simultaneously delivers (A) selectivity bootstrap, (B) gradient persistence across depth, and (C) per-step discrimination (e.g., \mathcal{L}_{sup} and \mathcal{L}_{node}). End-to-end supervision fails condition (B) and is provably insufficient: internal gradients at layer c decay as (np)^{-(D-c-2)/2} in the graph fan-out and stall before the manifold is reached. Our thesis: Möbius attractor + Cascade Supervision = emergence of superposition reasoning. The parameter-free decay law predicts a final-step cosine of 0.35 vs. 0.71 (end-to-end vs. cascade) at depth D=3; experiments confirm 0.37 vs. 0.69, matching within 0.02 at every step. --- ### Efficient Conditioning Why Pseudo Observation Batch Bayesian Optimization Works When It Does not Authors: Kumbha Nagaswetha, Rabi Pathak Published: 2026-05-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.18819v1 Constant Liar (CL), Kriging Believer (KB), and fantasy models are widely used for batch selection in parallel Bayesian Optimization, yet a unified theory explaining their effectiveness and conditions under which they fail has been lacking. We identify efficient conditioning as the key surrogate property the ability to update predictions in closed form when data is augmented. We prove that Gaussian Processes satisfy this requirement, producing provably distinct batch points with separation of order l, and that this holds for any acquisition function monotonically non decreasing in posterior uncertainty (EI, UCB, PI), with qualitatively similar behavior for Thompson Sampling. We unify CL, KB, and fantasy models as instances of a single conditioning mechanism differing only in the lie value distribution, and draw quantitative connections to Local Penalization (LP) and qualitative connections to Determinantal Point Processes (DPPs). To disentangle model structure from optimizer randomness, we introduce the Structural Diversity Diagnostic (SDD), a reusable methodology for testing surrogate compatibility. Experiments on Hartmann6D, Ackley 8D, Levy10D, and SVM hyperparameter tuning validate all theoretical predictions: CL or KBs implicit penalty matches or outperforms explicit LP greedy conditioning achieves convergence on par with joint qEI efficient conditioning extends to Multiquadric RBF networks; and parametric surrogates produce degenerate batches even when fully retrained (random forests), while neural networks regain diversity only at 15x the wall clock cost of GP conditioning. Robustness is confirmed across multiple initial datasets and under observation noise. --- ### Operationalizing Document AI: A Microservice Architecture for OCR and LLM Pipelines in Production Authors: Yao Fehlis, Benjamin Bengfort, Zhangzhang Si, Vahid Eyorokon, Prema Roman, Patrick Deziel, Devon Slonaker, Steve Veldman, Ben Johnson, Joyce Rigelo, Michael Wharton, Steve Kramer Published: 2026-05-12 Categories: cs.AI, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2605.18818v1 Academic research tends to focus on new models for document understanding creating a wide gap in the literature between model definition and running models at production scale. To close that gap, we present a microservice architecture that encapsulates pipelines of multiple models for classification, optical character recognition (OCR), and large language model structured field extraction as well as our experience running this pipeline on thousands of multi-page documents per hour. We describe our primary design decisions, including a hybrid classification, separation of GPU-bound inference from CPU-bound orchestration, use of asynchronous processing for the many IO-bound operations in the pipeline, and an independent, horizontal scaling strategy. Using batch profiling, we identified two surprising qualitative findings that shape production deployments: OCR, not language-model parsing, dominates end-to-end latency, and the system saturates at a concurrency determined by shared GPU-inference capacity rather than worker count. Our goal is to provide practitioners with concrete architectural patterns for building document understanding systems that work beyond the benchmark; effectively operationalizing models in production. --- ### Multi-Token Residual Prediction Authors: Yufeng Xu, Zishuo Bao, Qian Wang, Zeshen Zhang, Haoqi Zhang, Bowen Peng, Ang Li, Rahul Chalamala, Yucheng Lu Published: 2026-05-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.18817v2 Diffusion Language Models (DLMs) generate text by iteratively denoising masked token sequences, offering a tradeoff between parallelism and quality compared to autoregressive models. In current practice, the number of tokens decoded per step is controlled by a confidence threshold, and quality degrades monotonically as more tokens are denoised per step. We introduce Multi-token Residual Prediction (MRP), a lightweight module that enables dependency-aware multi-token denoising within a single backbone forward pass. MRP exploits a key property of the denoising process: the logit distributions at adjacent denoising steps are remarkably similar. Rather than running the backbone a second time to obtain the next-step logits, MRP predicts the residual between steps from the backbone's hidden states, effectively denoising more tokens per backbone forward at a fraction of the cost. We apply MRP across the two operating regimes of DLM decoding. In the high-quality-low-throughput static denoising regime, MRP serves as a drafter for speculative decoding: its proposals are verified against the backbone, yielding lossless acceleration of up to 1.4x in SGLang. In the low-quality-high-throughput dynamic denoising regime, MRP instead drives a remasking scheme that revokes over-eager reveals, recovering most of the accuracy lost to aggressive low-threshold decoding and improving accuracy by up to 22.6 points on code generation task HumanEval and 17.7 points on reasoning task GSM8K. --- ### When Does Equivariance Help? Canonical Alignment in Neural Fluid Surrogates Authors: Patryk Rygiel, Julian Suk, Kak Khee Yeung, Christoph Brune, Jelmer M. Wolterink Published: 2026-05-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.18816v2 Neural surrogates can accelerate computational fluid dynamics (CFD) simulations by orders of magnitude, but practical deployment in engineering and healthcare applications requires architectures that scale to high-resolution meshes and learn effectively from limited data. Explicit equivariance offers a principled inductive bias, yet its accuracy benefits may depend on the prediction task and the distribution of anatomical orientations. We investigate this dependence across three hemodynamic benchmarks with different degrees of natural canonical alignment. To support this study, we introduce the Anchored-Branched Geometric Algebra Transformer (AB-GATr), an $E(3)$-equivariant surrogate that efficiently predicts coupled surface and volume quantities. Across these benchmarks, AB-GATr consistently outperforms the evaluated non-equivariant models, including variants trained with rotational augmentation, while achieving accuracy competitive with $E(3)$-equivariant LaB-GATr at substantially lower training cost. In comparison, rotational augmentation provides inconsistent benefits across architectures and can reduce accuracy. A controlled experiment on ShapeNet-Car shows that strong canonical alignment can favor non-equivariant models, but their accuracy generally deteriorates as training orientations broaden and can decline sharply under broader test rotations. We further investigate these patterns using extended symmetry-breaking diagnostics and probes of the predictive information associated with canonical alignment across all benchmarks. Together, these results support explicit equivariance for the evaluated hemodynamic tasks with natural orientation variation, while showing that its accuracy benefits depend on the task and orientation distribution. --- ### Symmetry in the Wild: The Role of Equivariance in Neural Fluid Surrogates Authors: Patryk Rygiel, Julian Suk, Kak Khee Yeung, Christoph Brune, Jelmer M. Wolterink Published: 2026-05-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.18816v1 Neural surrogates enable orders-of-magnitude acceleration of computational fluid dynamics (CFD) simulations, with the potential to transform engineering and healthcare workflows. Neural surrogate use in real-world applications requires addressing scalability to large, high-resolution surface and volume meshes, as well as to bespoke architectures, and accounting for limited training data through the use of inductive biases. Group-equivariant architectures are a principled way to introduce such bias, yet they can be detrimental when the learning problem itself breaks symmetry, for example, due to strong distributional alignment in the dataset. In this work, we investigate under which conditions equivariance improves generalization in neural CFD surrogates across tasks with increasing levels of distributional alignment and realism, covering automotive aerodynamics and blood flow (hemodynamics). To systematically assess the added value of equivariance at the limit of problem scaling, we introduce the Anchored-Branched Geometric Algebra Transformer (AB-GATr), a neural surrogate that integrates scalability and symmetry preservation to efficiently model coupled surface and volume quantities in an $E(3)$-equivariant manner. We find that on strongly aligned aerodynamics datasets, i.e., those that break symmetry, enforcing equivariance can degrade in-distribution performance. In contrast, across hemodynamic benchmarks with diverse geometries and varying alignment, equivariance is consistently beneficial. Moreover, across all benchmarks, the explicit equivariance of AB-GATr reliably outperforms implicit symmetry learning through data augmentation. Our findings showcase that equivariance is not universally beneficial across domains, yet it brings tangible advantages in problems lacking strong data regularities. --- ### DynaTrain: Fast Online Parallelism Switching for Elastic LLM Training Authors: Yuanqing Wang, Yuchen Zhang, Hao Lin, Junhao Hu, Chunyang Zhu, Quanlu Zhang, Boxun Li, Guohao Dai, Zhi Yang, Daning Cheng, Yunquan Zhang, Yu Wang Published: 2026-05-12 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2605.18815v1 Modern large language model (LLM) training is inherently dynamic: resource fluctuations, RLHF phase shifts, and cluster elasticity continually reshape the optimal parallelism layout, posing a significant challenge to existing training frameworks built around a static execution model. We present DynaTrain, a distributed training system for sub-second, online reconfiguration across arbitrary multi-dimensional parallelism. At its core, we propose a Virtual Parameter Space (VPS) abstraction that unifies all distributed training states under one logical coordinate space, turning any parallelism configuration into a deterministic mapping and collapsing complex transition into manageable geometric intersections. On top of VPS, a state routing-and-transition layer executes rank-local transfers under a memory-aware, deadlock-free schedule, and an Elastic Device Manager overlaps new-world construction with ongoing training to mask topology-change cost. On dense and MoE models up to 235B parameters, DynaTrain reconfigures a 70B dense model in under 2s and a 235B MoE model in 4.36s, outperforming state-of-the-art checkpoint-based and elastic systems by up to three orders of magnitude while preserving correctness. --- ### How Faithful Is Trajectory-Based Data Attribution? Error Sources, Remedies, and Practical Guidelines Authors: Junwei Deng, Pingbang Hu, Suliang Jin, Hao Lu, Jiachen T. Wang, Shichang Zhang, Jiaqi W. Ma Published: 2026-05-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.18814v1 Trajectory-based data attribution methods estimate the influence of training samples on model predictions by unrolling the training trajectory. They are widely used in applications such as data selection, data valuation, and model diagnosis, but there is a lack of comprehensive error analysis of these methods, raising concerns about method faithfulness and hindering reliable deployment. In this work, we provide the first systematic analysis of error sources in trajectory-based data attribution, together with concrete remedies to mitigate them and practical guidelines for downstream use. We organize the total error into three categories, config-level, algorithm-level, and system-level. We make three contributions. First, we identify optimizer mismatch as the dominant config-level error: existing methods derive their attribution under the assumption of SGD, even for models trained with the modern de facto optimizer AdamW. We propose AdamW-influence to fully account for AdamW's optimization dynamics, yielding improvements from 10% to over 300% in Spearman correlation between estimated and ground-truth influence across four settings spanning MLP, CNN, GPT-2, and Llama 3.2-1B. Second, we isolate the remaining algorithm-level error arising from the first-order Taylor approximation, identify the learning rate and trajectory length as factors governing the error magnitude, and derive a closed-form error proxy that can be evaluated along the original trajectory without retraining. Third, we translate these insights into practical guidelines for data selection by unifying offline and online strategies under a K-step look-ahead framework. Under this framework, online selection with a short horizon often matches or exceeds offline, and the optimal horizon can be tuned jointly with the learning rate. Together, these results turn the framework into an actionable selection recipe for practitioners. --- ### Composition of Memory Experts for Diffusion World Models Authors: Sebastian Stapf, Pablo Acuaviva Huertos, Aram Davtyan, Paolo Favaro Published: 2026-05-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.18813v1 World models aim to predict plausible futures consistent with past observations, a capability central to planning and decision-making in reinforcement learning. Yet, existing architectures face a fundamental memory trade-off: transformers preserve local detail but are bottlenecked by quadratic attention, while recurrent and state-space models scale more efficiently but compress history at the cost of fidelity. To overcome this trade-off, we suggest decoupling future-past consistency from any single architecture and instead leveraging a set of specialized experts. We introduce a diffusion-based framework that integrates heterogeneous memory models through a contrastive product-of-experts formulation. Our approach instantiates three complementary roles: a short-term memory expert that captures fine local dynamics, a long-term memory expert that stores episodic history in external diffusion weights via lightweight test-time finetuning, and a spatial long-term memory expert that enforces geometric and spatial coherence. This compositional design avoids mode collapse and scales to long contexts without incurring a quadratic cost. Across simulated and real-world benchmarks, our method improves temporal consistency, recall of past observations, and navigation performance, establishing a novel paradigm for building and operating memory-augmented diffusion world models. --- ### PASC: Pipeline-Aware Conformal Prediction with Joint Coverage Guarantees for Multi-Stage NLP and LLM Pipelines Authors: Varun Kotte Published: 2026-05-12 Categories: cs.LG, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2605.18812v1 Modern NLP and LLM systems are pipelines: named entity recognition (NER) -> entity disambiguation (NED) -> entity typing, retrieval-augmented generation (retriever -> reader), and agentic chains of planner -> tool -> critic. Errors compound across stages, but existing uncertainty quantification methods either calibrate each stage independently (no joint coverage) or apply a Bonferroni union bound (joint coverage, but conservative). We present PASC (Pipeline-Aware Split Conformal), which reduces multi-stage joint coverage to a single scalar conformal prediction problem on the joint maximum nonconformity score. PASC provides a finite-sample distribution-free guarantee that all K stages are simultaneously covered with probability at least 1 - alpha, and is nearly tight up to a 1/(n+1) factor. On a three-stage NER -> NED -> entity-typing pipeline over CoNLL-2003, PASC achieves 96.4% end-to-end coverage versus 93.4% for Bonferroni and 86.5% for independent CP, at identical average prediction set size (1.083). Under distribution shift to WNUT-17 Twitter and WikiNEuRal Wikipedia data, PASC empirically maintains the target coverage in the tested shift settings while independent CP collapses to 59%. PASC requires a single quantile computation, runs 1.7x faster than Bonferroni, and scales to K = 6 stages where independent CP drops to 0.53 end-to-end coverage. The same joint-maximum-score reduction applies directly to compound LLM systems and agent pipelines. --- ### D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting Authors: Tianyu Wu, Yu Yao, Zhenting Qi, Han Zheng, Zhuohan Wang, Haoran Ma, Lawrence Liao, Himabindu Lakkaraju, Ju Li, Yilun Du Published: 2026-05-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.18810v1 Speculative decoding accelerates LLM inference by having a small drafter propose tokens that a larger target model verifies in parallel. Recent diffusion-based parallel drafters such as DFlash predict the full B-token block in one forward pass, enabling deeper drafters and longer accepted blocks. However, existing multi-token drafter objectives often use fixed position-dependent weighting schedules, such as head-dependent weights or block-position decays, which do not adapt as the positions limiting acceptance change during training. To address this, we derive per-position training weights from a differentiable surrogate of expected accepted draft length, matching the weight of each position to its log-probability gradient contribution. The resulting loss, D-PACE (Dynamic Position-Aware Cross-Entropy), shifts training signal toward positions that currently limit acceptance as the drafter improves. Across six benchmarks, two Qwen3-4B draft depths, two decoding temperatures, and two additional target models, D-PACE consistently improves both wall-clock speedup and average emitted length, with 2.3\% measured training-time overhead and no changes to the drafter architecture or inference procedure. --- ### Metric-Gradient Projection for Stable Multi-Agent Policy Learning Authors: Zuyuan Zhang, Sizhe Tang, Mahdi Imani, Tian Lan Published: 2026-05-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.18809v1 General-sum multi-agent learning is often governed by a stacked update field in which each agent's policy update changes the optimization landscape faced by the others. This coupling can entangle an integrable component of collective improvement with cyclic interaction dynamics, leading to slow or unstable multi-agent learning. Existing approaches, such as regularization, credit assignment, and consensus methods, stabilize MARL through local or algorithmic modifications; HPML complements them by projecting the joint update field onto a metric-gradient component. We introduce \textbf{HPML} (\textbf{H}odge-\textbf{P}rojected \textbf{M}ulti-agent \textbf{L}earning), which views the joint update field of a multi-agent system as an element of an $L^2$ space of vector fields and computes a Hodge-type projection onto the closest metric-gradient potential flow. HPML follows the projected component as the update direction, yielding the closest metric-gradient field under the chosen metric and sampling measure. The projection is defined variationally, characterized by a Poisson-type equation, and implemented through graph-based and amortized neural realizations that recover projected directions from samples. We show that the projected dynamics admit a Lyapunov potential and yield equilibrium-gap bounds with an explicit additive non-potentiality term. Controlled experiments validate the geometric mechanism, and CTDE benchmarks show improved stability and normalized return when HPML is used as a plug-in projection layer in MARL pipelines. --- ### CADS: Conformal Adaptive Decision System for Cost-Efficient Image Classification Authors: Mikael Turkoglu, Tim Bary, Vincent Thielens, Manon Dausort, Benoît Macq Published: 2026-05-12 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.16401v2 While high-capacity AI models have advanced state-of-the-art performance, their practical deployment is often hindered by high inference costs, environmental impact, and a "one-size-fits-all" approach that ignores varying sample complexity. In clinical settings for instance, the waste of computational resources on routine cases is a significant barrier to sustainable AI. In this paper, we introduce the Conformal Adaptive Decision System (CADS), a sequential multi-model algorithm designed to optimize resource allocation by efficiently sampling models based on the estimated data complexity. CADS leverages conformal prediction to quantify image uncertainty at runtime. CADS provides a mathematically grounded framework for balancing the cost-accuracy dilemma that dynamically routes samples through a model cascade, ranging from lightweight "Scout" models to high-capacity "Oracle" architectures. Validated on two datasets, CADS demonstrated superior efficiency and accuracy at a computational cost that can be up to 12 times lower than heavy-model inference. By accurately routing samples based on real-time complexity, CADS ensures high diagnostic reliability while drastically reducing the economic and environmental footprint of AI. --- ### Stable and Near-Reversible Diffusion ODE Solvers for Image Editing Authors: Barbora Barancikova, Daniil Shmelev, Cristopher Salvi Published: 2026-05-12 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.16399v2 The inversion of diffusion models plays a central role in image editing. Algebraically reversible ODE solvers provide an appealing approach to diffusion inversion for text-guided image editing, by eliminating the inversion error inherent in DDIM-based editing pipelines. However, empirical results indicate that reversibility alone is insufficient. As edits require larger semantic or visual changes, reversible diffusion solvers often exhibit instabilities and suffer sharp drops in output quality. In this paper, we show that the trade-off between exact reversibility and numerical stability manifests empirically as a trade-off between background preservation and prompt alignment in image editing. We then investigate the use of near-reversible Runge-Kutta methods as a more stable alternative to exactly reversible diffusion schemes. When combined with a vector-field smoothing strategy, the resulting approach improves edit fidelity, remains stable under large edits, and largely retains the background-preservation benefits of reversible solvers. --- ### Support-Safe Variational Hybrid Filtering for Contact-Mode and Sparse-Law Recovery Authors: Marios Papamichalis, Regina Ruane Published: 2026-05-12 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2605.16398v1 Contact-rich robot dynamics are hybrid: a single observation can match several latent states and contact regimes (free, impact, stick--slip). A standard amortized filter that places no probability on a feasible contact transition will permanently lose the branch the robot actually follows. We introduce VHYDRO, a variational hybrid dynamics learner that prevents this branch loss. At each step, VHYDRO mixes the learned proposal with a feasible transition law before sampling and importance weighting, ensuring that every transition retained by the model-feasible carrier remains covered. VHYDRO jointly infers a continuous latent state and a discrete contact mode, and fits a sparse port-Hamiltonian law to each recovered regime. On top of this, three guarantees connect: support coverage stabilizes filtering, the stabilized filter concentrates the discrete contact posterior on coherent regimes, and mode-pure segments admit sparse port-Hamiltonian recovery. The recovery error separates cleanly into filtering, derivative, mode-impurity, and physics-residual parts. Three empirical findings track the same mechanism. Under heavy occlusion the support-safe filter stays usable while a non-defensive proposal collapses. On ManiSkill demonstrations and on four Sawyer/BridgeData task families the discrete state forms temporally coherent contact-regime segments that the discrete state yields a stronger joint profile across ARI, change-point F1, and segment purity than post-hoc and mode-free baselines. On hybrid systems with known equations the mode-conditioned sparse fit recovers the active physical terms; purely predictive baselines do not. --- ### Trajectory-Aware Adaptive Inference in Object Detection Models Authors: Grigorios Papanikolaou, Ioannis Kontopoulos, Giannis Spiliopoulos, Dimitris Zissis, Konstantinos Tserpes Published: 2026-05-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.16397v1 The increasing integration of sensors in autonomous maritime navigation has led to large-scale multimodal datasets, raising challenges in achieving efficient real-time perception. In such systems, object detection and trajectory perception of nearby vessels are tightly coupled, particularly in dynamic environments such as maritime navigation. However, the efficiency of object detection models during inference remains an often-overlooked aspect. To this end, we build upon an existing object detection framework by incorporating GPS trajectory data into the inference process to enable input-adaptive computation. Specifically, we introduce an early-exit mechanism in a YOLOv8-based detector that incorporates motion cues - such as inter-vessel distances. Frames of vessels that are separated by short distances, converging with high speed, are processed using the full model, while only a subset of the network's architecture is activated otherwise. The difficulty degree (or scene complexity) of a frame or set of frames per second is evaluated by leveraging inter-object distance and the rate at which the distance between them decreases. Experimental results demonstrate that this strategy maintains satisfactory detection performance while significantly reducing inference time and computational cost, thus enabling a flexible trade-off between accuracy and efficiency compared to full-model inference. --- ### Beyond MMSE: Enhancing PnP Restoration with ProxiMAP Authors: Kenta Vert, Giacomo Meanti, Scott Pesme, Michael Arbel, Julien Mairal Published: 2026-05-12 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.16396v1 Plug-and-Play (PnP) methods have become standard tools for solving imaging inverse problems by replacing the intractable maximum a posteriori (MAP) denoiser with the MMSE one. While this mismatch has been widely treated as unavoidable, recent works have sought to close this gap by targeting the MAP with diffusion-model scores. We show this is problematic in practice: learned scores do not match the true ones, so MAP-targeting iterations converge to cartoon-like images rather than realistic ones, and better results are obtained by stopping short of convergence. We turn this observation into a design principle and introduce ProxiMAP, an iterative MAP approximation whose noise schedule keeps the iterate's residual noise matched to the denoiser's training noise. This keeps the denoiser in-distribution where its score is reliable, and yields implicit early stopping that avoids the failure mode above. ProxiMAP is a modular drop-in replacement for MMSE denoisers in standard PnP algorithms and consistently sharpens reconstructions across deblurring, inpainting, super-resolution, and phase retrieval. Building on the same principle, we propose a hybrid variant that applies ProxiMAP only in the late iterations of PnP, where the denoiser is most reliable -- matching or exceeding the full-replacement variant at a fraction of the cost. --- ### OrbiSim: World Models as Differentiable Physics Engines for Embodied Intelligence Authors: Jiajian Li, Jingyuan Huang, Junru Gong, Qi Wang, Xiaokang Yang, Yunbo Wang Published: 2026-05-12 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2605.16395v1 We present OrbiSim, a novel robotic simulation paradigm that redefines world models as a fully differentiable physics engine for embodied intelligence. Unlike prior world models that focus on unconstrained imagination in latent or visual domains, OrbiSim establishes a unified, physically-grounded pathway that bridges structured scene assets, neural dynamics, and downstream reinforcement learning. By enabling end-to-end differentiability throughout the entire simulation loop -- spanning from explicit state transitions to visual observation generation -- OrbiSim supports tasks traditionally intractable for classical simulators, such as differentiable contact modeling, gradient-based policy optimization under sparse rewards, and intuitive physical inference. Empirical results demonstrate that OrbiSim significantly outperforms state-of-the-art world models in both predictive fidelity and control performance. Furthermore, its consistent responsiveness to asset configurations and physical parameters suggests its potential as a differentiable tool for enhancing robot simulation and policy training. --- ### Vision Transformer-Conditioned UNet for Domain-Adaptive Semantic Segmentation Authors: Joel Valdivia Ortega, Tingying Peng, Marion Jasnin Published: 2026-05-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.16393v1 Semantic segmentation is essential for analysing anatomical features in biomedical research, yet a performance gap remains for Vision Transformers (ViTs) in the field, particularly for sparse, fine-structured, and low signal-to-noise targets. We attribute this challenge in part to the lightweight pixel decoders commonly used in promptable ViT models, who may lack the local inductive bias needed for high-precision biomedical masks. We bridge this gap by introducing ViTC-UNet, which conditions a UNet on frozen pre-trained ViT representations through learnable tokens and a two-way attention decoder. This combines ViT global visual priors with the local inductive bias and high-resolution decoding capacity of UNets, while avoiding end-to-end ViT fine-tuning even in cross-domain settings. ViTC-UNet outperforms baseline results in semantic segmentation tasks across MRI and CT modalities, demonstrating that structure-conditioned UNet decoding can efficiently adapt large-scale visual priors to high-complexity biomedical segmentation. --- ### Bridging the Modality Bottleneck in Pathology MIL through Virtual Molecular Staining Authors: Yucheng Xing, Pei Liu, Jingying Ma, Ruping Hong, Jiangdong Qiu, Tianyu Liu, Kai He, Ling Huang, Mengling Feng Published: 2026-05-12 Categories: q-bio.QM, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.16392v1 Multiple instance learning (MIL) is the dominant framework for whole-slide image analysis in computational pathology, typically combining a frozen patch encoder, a projection layer, and a slide-level aggregator. While encoders and aggregators have been extensively studied, the projection layer remains a largely morphology-only bottleneck. This limits endpoints such as biomarker status and survival, which are governed by a molecular state that is not fully captured by H&E morphology. We introduce Molecularly Informed Staining Transform (MIST), a plug-in replacement for the MIL projection layer that uses paired spatial transcriptomics only during training to construct virtual molecular stains. MIST clusters gene expression profiles into cross-modal prototypes, anchors them in the frozen foundation model feature space, and uses them to reorganize H&E patch features along molecularly guided axes. It requires no transcriptomics at inference and can be inserted before standard MIL aggregators. We evaluate MIST across 23 downstream tasks and 8 MIL aggregators. MIST improves 240 of 256 configurations over the standard projection layer, with an average gain of +3.5%, observed consistently across endpoint types: +5.2% on survival prediction, +3.3% on tissue subtyping, and +2.6% on biomarker prediction. Ablations confirm that gene-derived prototypes are the primary source of the gains, while spatial, biological, and pathological analyses show that cross-modal prototype affinities capture spatially coherent molecular programs from H&E alone. --- ### Overcoming the Intrinsic Performance Limitations of MEMS IMU via Diffusion-Based Generative Learning Authors: Jiarui Lv, Feng Zhu, Xiaohong Zhang Published: 2026-05-12 Categories: eess.SP, cs.AI, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2605.16391v1 Inertial measurement units (IMUs) are fundamental sensing components in multi-source integrated navigation systems, and their performance directly determines the accuracy and reliability of solutions. However, the precision of low-cost IMUs is inherently constrained by hardware limitations. Recently, generative artificial intelligence has demonstrated remarkable capability in modeling complex data distributions and reconstructing high-fidelity signals. Motivated by this, we propose a diffusion-based generative learning framework for synthesizing high-fidelity virtual IMU data from low-cost IMU measurements. Specifically, a conditional diffusion model based on a U-Net architecture is constructed, where high-grade IMU measurements are utilized as ground-truth priors and low-cost IMU measurements are employed as conditional inputs. The virtual IMU data generated by the model is used for subsequent navigation and localization tasks. Experimental results demonstrate that the generated virtual IMU data significantly outperform the original low-cost IMU measurements in both positioning and attitude estimation. Furthermore, we transfer the model to airborne mapping experiments, where the proposed method produces thinner and more consistent point clouds. Overall, the proposed framework breaks the performance limits of low-cost IMU and demonstrates the potential of diffusion-based generative learning for virtual high-grade IMU data. --- ### NOVA: Fundamental Limits of Knowledge Discovery Through AI Authors: Salman Avestimehr, Ken Duffy, Muriel Médard Published: 2026-05-12 Categories: cs.AI, cs.IT arXiv: https://arxiv.org/abs/2605.15219v3 Can AI systems discover new knowledge through iterative self-improvement, and at what cost? We introduce NOVA, which models the ``generate, verify, accumulate, retrain'' loop as an adaptive sampling process over a knowledge space. We give sufficient conditions for accumulated genuine knowledge to cover a finite domain and show how violations produce contamination, forgetting, exploration failure, and acceptance failure. We then analyze how adaptive generation arises from recursive retraining. In an explicit distribution-level model where accepted artifacts influence the next generator, we identify a recursive-feedback phase transition. Unanchored feedback can lock generation onto early accepted artifacts and leave initially reachable valid artifacts undiscovered with positive probability. Anchoring updates to a persistent base distribution prevents unbounded distortion and guarantees continued exposure. Under imperfect verification, we identify a contamination trap: as easy knowledge is exhausted, even small false-positive rates can admit invalid artifacts faster than genuine discoveries. We show that Good--Turing estimation is a local batch-diversity diagnostic, not an estimator of the historically undiscovered valid mass governing long-term progress. Under a Zipf tail with exponent $α>1$, the cumulative generation cost of obtaining $D$ distinct genuine discoveries satisfies $R_{\rm cum}(D)=Θ(c_{\rm gen}D^α)$. When the valid base distribution has such a tail, anchored retraining preserves the exposure needed for this scaling law. Finally, we show how human guidance, generation, and verification can redirect or expand discovery when autonomous sampling stalls because of repetition, vanishing exposure, or unreliable verification. --- ### CAX-Agent: A Lightweight Agent Harness for Reliable APDL Automation Authors: Chenying Lin, Yichen Hai, Yi He, Ran Wang, Haiyan Qiang, Liang Yu Published: 2026-05-12 Categories: cs.AI, cs.CE arXiv: https://arxiv.org/abs/2605.15218v1 Large language models deployed for MAPDL finite-element simulation face practical reliability challenges: without structured execution control, tool encapsulation, and fault recovery, outputs may be inconsistent and task failures are common. The Agent Harness paradigm addresses this by inserting domain-specific orchestration middleware that manages tool lifecycles, workflow state, and recovery escalation. This paper presents the architecture of CAX-Agent, a lightweight agent harness purpose-built for MAPDL automation, and empirically evaluates one of its core components -- the recovery policy.CAX-Agent organizes execution into three layers -- LLM service, agent harness, and solver backend -- with a recovery ladder that escalates from deterministic rule patching through model-driven regeneration to context enrichment and human intervention. We evaluate three recovery strategies (no_recovery, rule_only, and model_only) on 50 standard structural benchmarks with three repeated runs per strategy (450 case-runs total). Two independent human raters score task completion under blind conditions; inter-rater agreement is strong (quadratic weighted Cohen's kappa = 0.84, 96 percent of score pairs within one point). Model_only achieves the best completion rate (0.9267), task score (3.59/4), total score (9.16/10), and zero-intervention rate (0.84), outperforming rule_only (0.7733, 3.17/4, 7.03/10, 0.00) and no_recovery (0.6933, 2.74/4, 5.60/10, 0.00) with large effect sizes (Cliff's delta = 0.81-0.87). The benchmark uses deliberately simple geometries to isolate recovery-policy effects; we discuss the scope of these findings and directions for broader validation. --- ### Fair outputs, Biased Internals: Causal Potency and Asymmetry of Latent Bias in LLMs for High-Stakes Decisions Authors: Jagdish Tripathy, Marcus Buckmann Published: 2026-05-12 Categories: cs.AI, cs.CY, cs.LG, econ.GN arXiv: https://arxiv.org/abs/2605.15217v1 Instruction-tuned language models exhibit behavioural fairness in high-stakes decisions while retaining biased associations in their internal representations. However, whether these suppressed representations can affect model outputs - and whether such causal potency is symmetric across demographic groups - remains unknown. We investigate the use of open-weight models for mortgage underwriting using matched applications that differ only in racially-associated names and reveal a critical disconnect: models show no output-level bias, yet retain and amplify demographic representations across model layers. Through activation steering and novel cross-layer interventions, we demonstrate that this suppressed information is decision-relevant: when reinjected at critical layers, it produces near-complete decision reversals. Critically, this latent bias is asymmetric - steering interventions affect decisions in one demographic direction, while producing minimal effects in reverse - and susceptible to adversarial prompt engineering and parameter-efficient fine-tuning. These findings demonstrate that behavioural audits focused on outputs are insufficient: fair outputs can mask exploitable internal biases. They also motivate dual-layer testing frameworks combining output evaluation with representational analysis for AI governance in high-stakes decisions. --- ### Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computations Authors: Arthur Fyon, Julien Brandoit, Loris Mendolia, Damien Ernst, Jean-Michel Redouté, Guillaume Drion Published: 2026-05-12 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2605.15216v3 Always-on AI applications, from environmental sensors to biomedical implants, require ultra-low power consumption. Analog circuits offer a path to sub-microwatt inference, yet existing analog implementations are limited to feedforward architectures: extending them to recurrent dynamics has been considered impractical due to noise accumulation through temporal feedback. We demonstrate that this barrier can be overcome through hardware-software co-design. Specifically, we identify that Bistable Memory Recurrent Units (BMRUs), a class of Recurrent Neural Networks (RNNs) with discrete-valued outputs and hysteretic dynamics, admit an ultra-low power current-mode analog implementation which we design from first principles. The resulting circuit establishes a one-to-one correspondence between each learned parameter and a circuit element. The discrete outputs suppress analog noise by at least 20-fold at each cell boundary, breaking the noise accumulation that prevents analog recurrence. We reformulate BMRUs for first-quadrant operation with fixed thresholds, enabling the direct correspondence while preserving expressivity and trainability. Transistor-level simulations in 180 nm Complementary Metal-Oxide-Semiconductor (CMOS) show near-perfect agreement between software predictions and circuit-level behavior, with the software model thereby serving as a high-fidelity simulator of the physical hardware at low computational cost. We leverage this fidelity to conduct large-scale noise immunity and power scaling analyses: the power cost of adding recurrence scales linearly with state dimension, while the feedforward layers dominating total power scale quadratically, meaning recurrence is added at linear marginal cost relative to the feedforward backbone. End-to-end keyword spotting achieves sub-microwatt inference at the RNN core. --- ### SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces Authors: Duling Xu, Zheng Chen, Zaifeng Pan, Jiawei Guan, Dong Dong, Jialin Li, Bangzheng Pu Published: 2026-05-12 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2605.15215v1 Recently, skills have been widely adopted in large language model (LLM)-based agent systems across various domains. In existing frameworks, skills are typically injected into the agent reasoning loop as contextual guidance once matched to a runtime task, enabling specialized task-solving capabilities. We find that this execution paradigm introduces two major sources of redundancy: irrelevant context injection and repeated skill-specific reasoning and planning. To this end, we propose SkillSmith, a boundary-first compiler-runtime framework that compiles skill packages offline into minimal executable interfaces. By extracting fine-grained operational boundaries from skills, SkillSmith enables agents to dynamically access and execute only the relevant components at runtime, thereby minimizing unnecessary context injection and redundant reasoning overhead. In the evaluation on SkillsBench benchmark, SkillSmith reduces solve-stage token usage by 57.44%, thinking iterations by 42.99%, solve time by 50.57% (2.02x faster), and token-proportional monetary cost by 57.44% compared with using raw-skills. Moreover, compiled artifacts produced by a stronger model can be reused by a smaller or more efficient runtime model, improving task accuracy in cases where raw skill interpretation fails. The source code and data are available at https://github.com/AetherHeart-AI/Aeloon. ---